# LAION-SG: An Enhanced Large-Scale Dataset for Training Complex Image-Text Models with Structural Annotations

arXiv: https://arxiv.org/abs/2412.08580 · HTML: https://mlsanity.com/paper/2412.08580/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 59 references that are in the map.
- First posted on arXiv 11 Dec 2024.

## Builds on (most cited first, 30 of 30)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis](https://mlsanity.com/paper/2212.05032/) (2022)
- [LayoutGPT: Compositional Visual Planning and Generation with Large Language Models](https://mlsanity.com/paper/2305.15393/) (2023)
- [PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation](https://mlsanity.com/paper/2403.04692/) (2024)
- [T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation](https://mlsanity.com/paper/2307.06350/) (2023)
- [LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models](https://mlsanity.com/paper/2305.13655/) (2023)
- [Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs](https://mlsanity.com/paper/2401.11708/) (2024)
- [Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC](https://mlsanity.com/paper/2302.11552/) (2023)
- [Holistic Evaluation of Text-To-Image Models](https://mlsanity.com/paper/2311.04287/) (2023)
- [Benchmarking Spatial Relationships in Text-to-Image Generation](https://mlsanity.com/paper/2212.10015/) (2022)
- [Controllable Text-to-Image Generation with GPT-4](https://mlsanity.com/paper/2305.18583/) (2023)
- [Diffusion-Based Scene Graph to Image Generation with Masked Contrastive Pre-Training](https://mlsanity.com/paper/2211.11138/) (2022)
- [3DIS: Depth-Driven Decoupled Instance Synthesis for Text-to-Image Generation](https://mlsanity.com/paper/2410.12669/) (2024)
- [MIGC++: Advanced Multi-Instance Generation Controller for Image Synthesis](https://mlsanity.com/paper/2407.02329/) (2024)
- [IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation](https://mlsanity.com/paper/2410.07171/) (2024)
- [SG-Adapter: Enhancing Text-to-Image Generation with Scene Graph Guidance](https://mlsanity.com/paper/2405.15321/) (2024)
- [RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models](https://mlsanity.com/paper/2402.12908/) (2024)
- [IFAdapter: Instance Feature Control for Grounded Text-to-Image Generation](https://mlsanity.com/paper/2409.08240/) (2024)
- [Scene Graph Disentanglement and Composition for Generalizable Complex Image Generation](https://mlsanity.com/paper/2410.00447/) (2024)
- [Consistent Distributed Ranking of Generative Models via Kernel Distances](https://mlsanity.com/paper/2310.11714/) (2023)

## Built on by (most cited first, 12 of 12)

- [Is CLIP ideal? No. Can we fix it? Yes!](https://mlsanity.com/paper/2503.08723/) (2025)
- [Erasing More Than Intended? How Concept Erasure Degrades the Generation of Non-Target Concepts](https://mlsanity.com/paper/2501.09833/) (2025)
- [UniHOI: Unified Human-Object Interaction Understanding via Unified Token Space](https://mlsanity.com/paper/2511.15046/) (2025)
- [Inversion-DPO: Precise and Efficient Post-Training for Diffusion Models](https://mlsanity.com/paper/2507.11554/) (2025)
- [OmniFysics: Towards Physical Intelligence Evolution via Omni-Modal Signal Processing and Network Optimization](https://mlsanity.com/paper/2602.07064/) (2026)
- [Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization](https://mlsanity.com/paper/2605.28615/) (2026)
- [Augmenting Image Annotation: A Human-LMM Collaborative Framework for Efficient Object Selection and Label Generation](https://mlsanity.com/paper/2503.11096/) (2025)
- [Beyond Binary Preference: Aligning Diffusion Models to Fine-grained Criteria by Decoupling Attributes](https://mlsanity.com/paper/2601.04300/) (2026)
- [The Algorithmic Gaze of Image Quality Assessment: An Audit and Trace Ethnography of the LAION-Aesthetics Predictor](https://mlsanity.com/paper/2601.09896/) (2026)
- [MEPG:Multi-Expert Planning and Generation for Compositionally-Rich Image Generation](https://mlsanity.com/paper/2509.04126/) (2025)
- [RL-RIG: A Generative Spatial Reasoner via Intrinsic Reflection](https://mlsanity.com/paper/2602.19974/) (2026)
- [Curation Leaks: Membership Inference Attacks against Data Curation for Machine Learning](https://mlsanity.com/paper/2603.00811/) (2026)

## Abstract (arXiv)

Recent advances in text-to-image (T2I) generation have shown remarkable success in producing high-quality images from text. However, existing T2I models show decayed performance in compositional image generation involving multiple objects and intricate relationships. We attribute this problem to limitations in existing datasets of image-text pairs, which lack precise inter-object relationship annotations with prompts only. To address this problem, we construct LAION-SG, a large-scale dataset with high-quality structural annotations of scene graphs (SG), which precisely describe attributes and relationships of multiple objects, effectively representing the semantic structure in complex scenes. Based on LAION-SG, we train a new foundation model SDXL-SG to incorporate structural annotation information into the generation process. Extensive experiments show advanced models trained on our LAION-SG boast significant performance improvements in complex scene generation over models on existing datasets. We also introduce CompSG-Bench, a benchmark that evaluates models on compositional image generation, establishing a new standard for this domain. Our annotations with the associated processing code, the foundation model and the benchmark protocol are publicly available at https://github.com/mengcye/LAION-SG.